Update app.py

app.py

@@ -1,8 +1,9 @@
 import os
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import StreamingResponse
-import openai  # Use OpenAI's official API library
+from openai import AsyncOpenAI
 from pydantic import BaseModel
+import httpx
 
 # Initialize FastAPI app
 app = FastAPI()
@@ -16,41 +17,49 @@ token = os.getenv("GITHUB_TOKEN")
 if not token:
     raise ValueError("GITHUB_TOKEN environment variable not set")
 
-# Initialize OpenAI API client with API key
-openai.api_key = token  # Set the OpenAI API key
+# Use environment variables for endpoint and model, with fallbacks
+endpoint = os.getenv("API_ENDPOINT", "https://api.openai.com/v1")  # Fallback to OpenAI-compatible endpoint
+model = os.getenv("MODEL_NAME", "gpt-4o-mini")  # Default to a known model
 
-# Async generator to stream chunks from OpenAI's API
+# Initialize AsyncOpenAI with a custom HTTP client to avoid proxies issue
+client = AsyncOpenAI(
+    base_url=endpoint,
+    api_key=token,
+    http_client=httpx.AsyncClient()  # Explicitly use httpx.AsyncClient without proxies
+)
+
+# Async generator to stream chunks
 async def stream_response(prompt: str):
     try:
-        # Create streaming chat completion with OpenAI API
-        response = openai.ChatCompletion.create(
-            model="gpt-4",  # Replace with the model you're using (e.g., gpt-3.5-turbo or gpt-4)
+        # Create streaming chat completion
+        stream = await client.chat.completions.create(
             messages=[
                 {"role": "system", "content": "You are a helpful assistant."},
                 {"role": "user", "content": prompt}
             ],
             temperature=1.0,
             top_p=1.0,
-            stream=True  # Enable streaming
+            model=model,
+            stream=True
         )
 
-        # Yield each chunk of the response as it arrives
-        for chunk in response:
-            content = chunk.get("choices", [{}])[0].get("delta", {}).get("content", "")
-            if content:
-                yield content  # Yield the generated content
+        # Yield each chunk as it arrives
+        async for chunk in stream:
+            if chunk.choices and len(chunk.choices) > 0:
+                content = chunk.choices[0].delta.content or ""
+                if content:
+                    yield content
 
     except Exception as err:
         yield f"Error: {str(err)}"
 
-# Endpoint to handle the prompt and stream response
+# Endpoint to handle prompt and stream response
 @app.post("/generate")
 async def generate_response(request: PromptRequest):
     try:
-        # Return a StreamingResponse with the async generator
         return StreamingResponse(
             stream_response(request.prompt),
-            media_type="text/event-stream"  # Use text/event-stream for streaming
+            media_type="text/event-stream"
         )
     except Exception as err:
         raise HTTPException(status_code=500, detail=f"Server error: {str(err)}")
@@ -58,4 +67,4 @@ async def generate_response(request: PromptRequest):
 # Health check endpoint for Hugging Face Spaces
 @app.get("/")
 async def health_check():
-    return {"status": "healthy"}
+    return {"status": "healthy"}